CoreWeave
Search…
⌃K

Examples and Tutorials

Try out Inference on CoreWeave by following our in-depth walkthrough guides

Inference tutorial directory

Each tutorial page includes a link to the source code for the provided example. In most cases, it will be required to clone the repository in order to follow along directly with the tutorial's walkthrough.

One-Click models

Title
Description
​GPT-J-6B​
Deploy popular open source model GPT-J-6B with the click of a button

PyTorch

Title
Description
Input a text prompt to generate high-quality images with photorealistic capabilities
Deploy BLOOM as an InferenceService with a simple HTTP API to perform Text Generation using Transformers Accelerate
Deploy BLOOM as an InferenceService with a simple HTTP API to perform Text Generation using Transformers DeepSpeed
Deploy the new text generation toolchain for GPT-2, aitextgen, using a custom predictor
Deploying a sentiment analyzer built with FastAI, using a custom predictor

TensorFlow

Serve and use the OpenAI GPT-2 text generation model with this multi-part guide
Step-by-step instructions are not published for this example - the deployment process is identical to the steps used in the GPT-2 Tensorflow example, save for the provided source code

Triton Inference

Deploy EleutherAI GPT-J and GPT-NeoX on NVIDIA Triton Inference Server with the FasterTransformer backend via an InferenceService using an HTTP API to perform Text Generation

JAX

Use a text prompt as input to generate an image as output using DALL-E Mega​

Custom

​BASNET​
Deploy an auto-scaling Inference service from a pre-existing Docker image
Note
For PyTorch, use pip to install PyTorch bundled with CUDA. Do not install CUDA separately, as doing so may result in dependency mismatches. For more information, refer to the PyTorch installation guide.
Previous
Get Started with Inference
Next
One-Click Models
Last modified 1mo ago